中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
INformer: Inertial-Based Fusion Transformer for Camera Shake Deblurring

文献类型：期刊论文

作者Ren, Wenqi1; Wu, Linrui1; Yan, Yanyang2; Xu, Shengyao3; Huang, Feng3; Cao, Xiaochun1
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2024
卷号33页码:6045-6056
关键词Camera shake deblurring inertial measurement units deformable attention Camera shake deblurring inertial measurement units deformable attention
ISSN号1057-7149
DOI10.1109/TIP.2024.3461967
英文摘要Inertial measurement units (IMU) in the capturing device can record the motion information of the device, with gyroscopes measuring angular velocity and accelerometers measuring acceleration. However, conventional deblurring methods seldom incorporate IMU data, and existing approaches that utilize IMU information often face challenges in fully leveraging this valuable data, resulting in noise issues from the sensors. To address these issues, in this paper, we propose a multi-stage deblurring network named INformer, which combines inertial information with the Transformer architecture. Specifically, we design an IMU-image Attention Fusion (IAF) block to merge motion information derived from inertial measurements with blurry image features at the attention level. Furthermore, we introduce an Inertial-Guided Deformable Attention (IGDA) block for utilizing the motion information features as guidance to adaptively adjust the receptive field, which can further refine the corresponding blur kernel for pixels. Extensive experiments on comprehensive benchmarks demonstrate that our proposed method performs favorably against state-of-the-art deblurring approaches.
资助项目National Natural Science Foundation of China[62322216] ; National Natural Science Foundation of China[62172409] ; National Natural Science Foundation of China[62302480] ; Shenzhen Science and Technology Program[RCYX20221008092849068] ; Shenzhen Science and Technology Program[JCYJ20220818102012025] ; Shenzhen Science and Technology Program[JCYJ20220530145209022]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001342519900006
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/39465]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Yan, Yanyang
作者单位1.Sun Yat Sen Univ, Sch Cyber Secur, Shenzhen 518107, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China
3.Fuzhou Univ, Coll Mech Engn & Automat, Fuzhou 350108, Peoples R China
推荐引用方式
GB/T 7714		 Ren, Wenqi,Wu, Linrui,Yan, Yanyang,et al. INformer: Inertial-Based Fusion Transformer for Camera Shake Deblurring[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:6045-6056.
APA Ren, Wenqi,Wu, Linrui,Yan, Yanyang,Xu, Shengyao,Huang, Feng,&Cao, Xiaochun.(2024).INformer: Inertial-Based Fusion Transformer for Camera Shake Deblurring.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,6045-6056.
MLA Ren, Wenqi,et al."INformer: Inertial-Based Fusion Transformer for Camera Shake Deblurring".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):6045-6056.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。